Upcoming Talks

Ista white

Integrating Algorithms into Neural Networks

Date
Thursday, March 24, 2022 15:15 - 17:00
Speaker
Felix Peterson (University of Konstanz )
Location
Join Zoom Meeting https://istaustria.zoom.us/j/69657308623?pwd=MTdLS1I4T084cU43OEs3TFN2NjNHdz09 Meeting ID: 696 5730 8623 Passcode: 098438
Series
Seminar/Talk
Tags
Talk
Host
Christoph Lampert
Contact
Ksenja Harpprecht

Classic algorithms and machine learning systems like neural networks

are both abundant in everyday life. While classic computer

science algorithms are suitable for precise execution of exactly defined

tasks such as finding the shortest path in a large graph, neural

networks allow learning from data to predict the most likely answer in

more complex tasks such as image classification, which cannot be

reduced to an exact algorithm. In the talk, we explore combining

both concepts leading to more robust, better performing, more interpretable,

more computationally efficient, and most importantly data

efficient architectures. Using algorithmic supervision a neural network can learn

from or in conjunction with an algorithm. When integrating an algorithm

into a neural architecture, it is important that the algorithm is

differentiable such that the architecture can be trained end-to-end and

gradients can be propagated back through the algorithm in a meaningful

way. To make algorithms differentiable, I discuss a general

method for continuously relaxing algorithms by perturbing variables

with logistic distributions. In addition, I discuss specialized differentiable

algorithms such as differentiable sorting networks, and efficient

and effective differentiable sorting and ranking operators allowing

sorting and ranking supervision. Furthermore, I delve into differentiable

rendering, specifically, the generalized differentiable renderer GenDR.


Qr image
Download ICS Download invitation
Back to eventlist